Interpretability Is in the Mind of the Beholder: A Causal Framework for Human-Interpretable Representation Learning.
Emanuele MarconatoAndrea PasseriniStefano TesoPublished in: Entropy (2023)
Keyphrases
- learning process
- learning scheme
- learning systems
- supervised learning
- main contribution
- learning algorithm
- prior knowledge
- learning tasks
- human experts
- perceptual information
- multiple representations
- distributed learning
- inference process
- language acquisition
- visual representation
- computational model
- online learning
- multi task
- computational models
- dynamic bayesian networks
- unsupervised learning
- knowledge acquisition
- reinforcement learning
- learning frameworks
- artificial intelligence